Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    states, outcomes, or possessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distillate
    0.49
     moduli
    0.49
     radiator
    0.48
     glial
    0.47
     workpiece
    0.47
     conditioners
    0.47
     radiative
    0.47
     hadrons
    0.46
     radiographic
    0.46
     parameters
    0.46
    POSITIVE LOGITS
     Bollywood
    0.67
     Entrepreneur
    0.52
     Entertainment
    0.52
     Tourism
    0.52
     Untold
    0.51
     Spectacular
    0.51
    映画
    0.50
     Culture
    0.50
     Festivals
    0.50
     Creativity
    0.49
    Act Density 0.006%

    No Known Activations